GPTSwarm: evolutionary graph optimisation
Reproducing adversarial multi-agent LLM experiments and comparing REINFORCE with an evolutionary edge optimiser.
Team projectReport
✳ Artificial intelligence & applied research
Baran
Akkanat.
MSc Artificial Intelligence
University of Groningen
My interests include machine learning, explainable AI and human-centred systems. I combine an electrical engineering background with research and software development.
Electrical & Electronics Engineering · Ankara University
Conceptual visualisationInteractive graphic
Machine learning and representation.
Research interests
Machine learning
✳Human-centred AI
✳Explainable AI
Academic work
Research projects
Research questions, methods and findings.
Full reports accompany each project.
Browse all reports →
SentenceBot
An Alpha Mini prototype combining tangible topic selection, adaptive difficulty and language-model feedback.
Team project2 reports
Fairness & explainability
Looking beyond prediction scores to understand how fairness interventions change decisions and feature attributions.
Team project2 reports
Conditioning diffusion transformers
A controlled comparison of adaptive layer normalisation and cross-attention for text-conditioned image generation.
Team projectReport
Dreaming agents
Tabular reinforcement learning with replay and perturbed experience in a small GridWorld.
Individual projectReport
Sign language recognition
Transfer learning with MobileNetV2, evaluated on people held out from training.
Team projectReport
Cognitive modelling with ACT-R
A declarative-memory model examining how social comparison changes contributions in a public goods game.
Individual projectReport
Recursive theory of mind
Bounded reasoning about what agents know, observe and believe about one another.
Individual projectReport
Multi-agent social simulation
Analysing relationships and survival dynamics in a constructed social environment.
Team projectReport
Responsible AI for urban traffic
A conceptual traffic-management proposal examining privacy, stakeholder needs and human oversight.
Team design studyReport
Selected work
Software development
Independent software projects
and applied engineering.
Independent productMedix
Clinic workflow management.
A clinic operating system that brings scheduling, patient workflows and team permissions together, with privacy built into the way work gets done.
Read engineering reportPortfolio illustration · synthetic content
Academic background
Education & experience
I am a master’s student in Artificial Intelligence at the University of Groningen.
I hold a bachelor’s degree in Electrical and Electronics Engineering from Ankara University. My current academic work covers machine learning, explainability and cognitive modelling.
I am preparing for a research internship at WLN on AI-supported knowledge access in a scientific organisation. Alongside my studies, I develop Medix, an independent clinic management application.
PythonPyTorchScikit-learnTypeScriptNext.jsPostgreSQL
Education
MSc Artificial Intelligence
University of Groningen
In progress. Academic projects in machine learning, explainability, deep learning and cognitive modelling.
Bachelor’s degree, Electrical and Electronics Engineering
Ankara University
Undergraduate work & reportsExperience
Research internship
WLN · Waterlaboratorium Noord
Planned research on AI-supported knowledge access using a requirements-driven approach. The internship has not yet started.
Summer intern
KIBTEK · Teknecik Power Plant
Observation of steam, gas and diesel generation systems, control-room operations and electrical maintenance. The placement is documented in a 39-page internship report.
Other interests
Music production
I produce music and work on mixing and mastering under the name RMDN. RMDNBEATZ is the associated music project.
Audio only plays when you choose. Spotify loads on request.
Contact
Contact
For research enquiries and professional correspondence.